Tank Model Coupled with an Artificial Neural Network

Cerda-Villafana, G.; Ledesma, Sergio; Gonzalez-Ramirez, E.

doi:10.1007/978-3-540-88636-5_33

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abrahart et al (2012) present recent ANN applications and procedures in streamflow modelling and forecasting, which include modular design concepts, ensemble experiments, and hybridization of ANNs with typical hydrological models. Furthermore, ANNs have been used for combining the outputs of different rainfall-runoff models in order to improve the prediction and modelling of streamflow (Shamseldin et al, 1997;Chen and Adams, 2006;Kim et al, 2006;Nilsson et al, 2006;Cerda-Villafana et al, 2008;Liu et al, 2013) and the river flow forecasting (Brath et al, 2002;Shamseldin et al, 2002;Anctil et al, 2004a;Srinivasulu and Jain, 2009;Elshorbagy et al, 2010;Mount et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Streamflow simulation methods for ungauged and poorly gauged watersheds

Λουκάς

Vasiliades

2014

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Rainfall-runoff modelling procedures for ungauged and poorly gauged watersheds are developed in this study. A well-established hydrological model, the University of British Columbia (UBC) watershed model, is selected and applied in five different river basins located in Canada, Cyprus, and Pakistan. Catchments from cold, temperate, continental, and semiarid climate zones are included to demonstrate the procedures developed. Two methodologies for streamflow modelling are proposed and analysed. The first method uses the UBC watershed model with a universal set of parameters for water allocation and flow routing, and precipitation gradients estimated from the available annual precipitation data as well as from regional information on the distribution of orographic precipitation. This method is proposed for watersheds without streamflow gauge data and limited meteorological station data. The second hybrid method proposes the coupling of UBC watershed model with artificial neural networks (ANNs) and is intended for use in poorly gauged watersheds which have limited streamflow measurements. The two proposed methods have been applied to five mountainous watersheds with largely varying climatic, physiographic, and hydrological characteristics. The evaluation of the applied methods is based on the combination of graphical results, statistical evaluation metrics, and normalized goodness-of-fit statistics. The results show that the first method satisfactorily simulates the observed hydrograph assuming that the basins are ungauged. When limited streamflow measurements are available, the coupling of ANNs with the regional, non-calibrated UBC flow model components is considered a successful alternative method to the conventional calibration of a hydrological model based on the evaluation criteria employed for streamflow modelling and flood frequency estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Streamflow simulation methods for ungauged and poorly gauged watersheds

Λουκάς

Vasiliades

2014

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…In order to successfully simulate the rainfall and runoff processes, most researchers and hydrologists work by two kinds of mainstreams consisting of deterministic techniques that take underlying physical processes into account, such as TOPMODEL [1,2] and the systems theoretic models that care about only the inputs and outputs of the whole watershed but possess the ability to capture the complicated non-linear relationship, such as ANN [3][4][5]. Moreover, some studies combine the two tools for better results [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

A Novel Integrated Rainfall-Runoff Model Based on TOPMODEL and Artificial Neural Network

Liu

Zhao

et al. 2013

AMM

View full text Add to dashboard Cite

Conventional process-based rainfall-runoff models are difficult to catch the non-linear factors and to take full advantages of previous information of rainfall and runoff. However, these factors are closely related to the initial watershed average saturation deficit at each time step. Therefore, in order to address the issue, this study selected the parameter about initial underground flow in TOPMODEL (TOPOgraphic driven Model) as the breakthrough point. Then we used the previous two-day observed runoff and rainfall data as the inputs of an artificial neural network (ANN) and initial subsurface flow of present day as an output, then integrated ANN into runoff generation module in TOPMODEL and finally applied the integrated model for daily runoff modeling in Yingluoxia watershed with 10009km2, China. In addition, this work also utilized particle swarm optimization technique (PSO) to avoid the local optimization, especially for the integration of black-box and physical models. The result shows that during the validation period the Nash-Sutcliffe efficiency coefficient (NE) and root mean square error (RMSE) of TOPMODEL are 0.45 and 3.88×10-4m respectively while the NE of 0.70 and RMSE of 2.85×10-4m for the integrated model. Significantly, the integrated model performs much better than the traditional model. Hence, this new method of integrating ANN with the runoff generation module of TOPMODEL is promising and easily extended to other process-based rainfall-runoff models as well.

show abstract

An innovative method for dynamic update of initial water table in XXT model based on neural network technique

Liu

Jun

et al. 2013

Applied Soft Computing

View full text Add to dashboard Cite

Tank Model Coupled with an Artificial Neural Network

Cited by 4 publications

References 6 publications

Streamflow simulation methods for ungauged and poorly gauged watersheds

Streamflow simulation methods for ungauged and poorly gauged watersheds

A Novel Integrated Rainfall-Runoff Model Based on TOPMODEL and Artificial Neural Network

An innovative method for dynamic update of initial water table in XXT model based on neural network technique

Contact Info

Product

Resources

About